Skip to main content

Before you start

Complete organization setup, make sure your account has inference credit, and create a key on the API Keys page. Most coding agents need a tool-capable chat model; Aider’s basic edit workflow does not require native tool calling. Image input and reasoning support depend on the model. These terminal examples use Bash or Zsh on macOS, Linux, or Windows through WSL. Use your existing Open WebUI instance or follow its official installation guide. You need administrator access to add a shared provider connection. Installation instructions.

Get your connection settings

Open Integrations, select a model, then choose Open WebUI. The screen uses your organization’s region. The examples below use the public global endpoint; replace it with your regional endpoint and replace YOUR_MODEL_ID with the full model ID shown there. Choose one of the models listed for this integration. Paste your Pearl API key into Open WebUI’s API key field. Enter the key itself, not an environment variable name.

Configure Open WebUI

In the Admin Panel, open Settings, then Connections, and add an OpenAI API connection. Enter the Pearl URL and your key with Bearer auth, and keep the API Type at Chat Completions. Provider and Model IDs are in the Advanced section: leave Provider at Default and add the exact model ID to Model IDs. Verify the connection, then save. Menu names can differ between Open WebUI releases.
Open WebUI connection fields

Start using Open WebUI

Open a new chat, select the Pearl model, and send a message. Enable tools or image input only when supported by that model.

Troubleshooting

Saving is separate from verifying the connection. If verification fails, check the URL and key. If the model is missing from the chat model list, check that its exact ID is in Model IDs. Open WebUI can send its built-in tools with each chat, which adds input tokens to every message. Embeddings, speech, and image generation require separately supported services and are not part of this connection.
  • 401: check the key and allow time for a newly created key to reach the inference gateway.
  • 404: copy the endpoint and exact model ID from Integrations. OpenAI base URLs end in /v1; the Anthropic SDK and Claude Code use the URL without that suffix.
  • 402: check your organization’s credit and billing status.
  • 429 or Anthropic 529: respect retry instructions and reduce concurrency.
  • For truncated output, check the output limit and reasoning budget. Increase limits only within the model’s maximum output length.